Competition to deploy commercial brain-computer interfaces is heating up. A microelectronic chip placed under the retina can produce vision. Science Corporation--a competitor to Neuralink founded by the former president of Elon Musk's brain-interface venture--has leapfrogged its rival after acquiring, at a fire-sale price, a vision implant that's in advanced testing,. The implant produces a form of "artificial vision" that lets some patients read text and do crosswords, according to a report published in the today . The implant is a microelectronic chip placed under the retina. Using signals from a camera mounted on a pair of glasses, the chip emits bursts of electricity in order to bypass photoreceptor cells damaged by macular degeneration, the leading cause of vision loss in elderly people.

Recent advances in reasoning-focused large language models (LLMs) mark a shift from general LLMs toward models designed for complex decision-making, a crucial aspect in medicine. However, their performance in specialized domains like ophthalmology remains underexplored. This study comprehensively evaluated and compared the accuracy and reasoning capabilities of four newly developed reasoning-focused LLMs, namely DeepSeek-R1, OpenAI o1, o3-mini, and Gemini 2.0 Flash-Thinking. Each model was assessed using 5,888 multiple-choice ophthalmology exam questions from the MedMCQA dataset in zero-shot setting. Quantitative evaluation included accuracy, Macro-F1, and five text-generation metrics (ROUGE-L, METEOR, BERTScore, BARTScore, and AlignScore), computed against ground-truth reasonings. Average inference time was recorded for a subset of 100 randomly selected questions. Additionally, two board-certified ophthalmologists qualitatively assessed clarity, completeness, and reasoning structure of responses to differential diagnosis questions.O1 (0.902) and DeepSeek-R1 (0.888) achieved the highest accuracy, with o1 also leading in Macro-F1 (0.900). The performance of models across the text-generation metrics varied: O3-mini excelled in ROUGE-L (0.151), o1 in METEOR (0.232), DeepSeek-R1 and o3-mini tied for BERTScore (0.673), DeepSeek-R1 (-4.105) and Gemini 2.0 Flash-Thinking (-4.127) performed best in BARTScore, while o3-mini (0.181) and o1 (0.176) led AlignScore. Inference time across the models varied, with DeepSeek-R1 being slowest (40.4 seconds) and Gemini 2.0 Flash-Thinking fastest (6.7 seconds). Qualitative evaluation revealed that DeepSeek-R1 and Gemini 2.0 Flash-Thinking tended to provide detailed and comprehensive intermediate reasoning, whereas o1 and o3-mini displayed concise and summarized justifications.

Artificial intelligence (AI) has gained significant attention in healthcare consultation due to its potential to improve clinical workflow and enhance medical communication. However, owing to the complex nature of medical information, large language models (LLM) trained with general world knowledge might not possess the capability to tackle medical-related tasks at an expert level. Here, we introduce EyeGPT, a specialized LLM designed specifically for ophthalmology, using three optimization strategies including role-playing, finetuning, and retrieval-augmented generation. In particular, we proposed a comprehensive evaluation framework that encompasses a diverse dataset, covering various subspecialties of ophthalmology, different users, and diverse inquiry intents. Moreover, we considered multiple evaluation metrics, including accuracy, understandability, trustworthiness, empathy, and the proportion of hallucinations. By assessing the performance of different EyeGPT variants, we identify the most effective one, which exhibits comparable levels of understandability, trustworthiness, and empathy to human ophthalmologists (all Ps>0.05). Overall, ur study provides valuable insights for future research, facilitating comprehensive comparisons and evaluations of different strategies for developing specialized LLMs in ophthalmology. The potential benefits include enhancing the patient experience in eye care and optimizing ophthalmologists' services.

Socially assistive robots (SARs) have shown great promise in supplementing and augmenting interventions to support the physical and mental well-being of older adults. However, past work has not yet explored the potential of applying SAR to lower the barriers of long-term low vision rehabilitation (LVR) interventions for older adults. In this work, we present a user-informed design process to validate the motivation and identify major design principles for developing SAR for long-term LVR. To evaluate user-perceived usefulness and acceptance of SAR in this novel domain, we performed a two-phase study through user surveys. First, a group (n=38) of older adults with LV completed a mailed-in survey. Next, a new group (n=13) of older adults with LV saw an in-clinic SAR demo and then completed the survey. The study participants reported that SARs would be useful, trustworthy, easy to use, and enjoyable while providing socio-emotional support to augment LVR interventions. The in-clinic demo group reported significantly more positive opinions of the SAR's capabilities than did the baseline survey group that used mailed-in forms without the SAR demo.

Diabetic retinopathy is a serious and potentially blinding complication of diabetes. Despite significant advances in the treatment of the disease, it remains a leading cause of vision loss in adults worldwide. What makes diabetic retinopathy particularly dangerous is that it is often asymptomatic in its early stages, meaning patients may not even know they have the disease until it has progressed significantly. By this point, the damage to the eyes can be irreversible, making early detection and treatment crucial. Screening for diabetic retinopathy can be a challenging task for ophthalmologists and healthcare providers.

Did you know that India has the dubious honour of being the Diabetes Capital of the World?1. The estimates show that India's diabetes burden is increasing, and it is doing so at a rapid clip. The International Diabetes Federation Atlas 2019 estimated that there are roughly 77 million cases of diabetes in the adult population of India as of 2019. It also predicts that this number will climb to 101 million in 2030 and to 134 million in 20452. The disease burden of diabetes doesn't come from diabetes alone, but the various complications that go hand in hand with it.

By 2050, the National Institute of Health (NIH) National Eye Institute estimates that 14.6 million Americans will have diabetic retinopathy. A new study published in The Lancet demonstrates how artificial intelligence (AI) machine learning can screen in real-time for diabetic retinopathy--a leading cause of preventable blindness, particularly in areas with low-income or middle-income economies. According to the Centers for Disease Control (CDC), one in four American adults with vision loss reported anxiety or depression. Moreover, vision loss has been linked to fear, anxiety, worry, social isolation, and loneliness. Scientists affiliated with Google Health and their collaborators applied artificial intelligence (AI) machine learning to detect one of the most common causes of preventable blindness--diabetic retinopathy.

In a country such as India that has a low doctor-patient ratio, Artificial Intelligence (AI) can enable greater access to expert care from anywhere, with telehealth and robotics applied across inpatient and outpatient environments. Experts says AI will bolster the role of healthcare by assisting in screening, diagnosis, and treatment of diseases thereby improving quality of life and reducing the cost burden for patients. "India has a tremendous opportunity to lead human-centric applications and democratise AI for the world backed by high skilled talent, technology, vast data availability, and the potential for population-scale AI adoption," says Vice-president and managing director of Sales, Marketing and Communications Group, Intel India. Intel has been focusing its efforts towards accelerating AI innovation to deliver transformative healthcare solutions and democratise healthcare access and delivery in India. The company's portfolio of compute, memory, storage, and networking technologies powers some of the most exciting healthcare and life sciences applications.

In a country such as India that has a low doctor-patient ratio, Artificial Intelligence (AI) can enable greater access to expert care from anywhere, with telehealth and robotics applied across inpatient and outpatient environments. Experts says AI will bolster the role of healthcare by assisting in screening, diagnosis, and treatment of diseases thereby improving quality of life and reducing the cost burden for patients. "India has a tremendous opportunity to lead human-centric applications and democratise AI for the world backed by high skilled talent, technology, vast data availability, and the potential for population-scale AI adoption," says Prakash Mallya, vice-president and managing director of Sales, Marketing and Communications Group, Intel India. Intel has been focusing its efforts towards accelerating AI innovation to deliver transformative healthcare solutions and democratise healthcare access and delivery in India. The company's portfolio of compute, memory, storage, and networking technologies powers some of the most exciting healthcare and life sciences applications. The cloud-based AI solution Netra.AI is the latest example of the impact and innovation that can be made possible with Intel technology.

Intel has focused its efforts on accelerating artificial intelligence innovation to deliver transformative healthcare solutions and democratize healthcare access and delivery in India. The company’s portfolio of computing, memory, storage and networking technologies powers some of the most exciting life sciences and health applications. The Netra.AI cloud-based artificial intelligence solution is the latest example of the impact and innovation that can be made possible by Intel technology. The solution uses deep learning to identify retinal conditions in a short period of time with the level of precision of human physicians. Netra.AI can accurately identify diabetic retinopathy (DR), greatly reducing the detection burden for vitreoretinal surgeons. The solution analyzes images from technician-operated portable fundus camera devices for immediate transferable DR score results via a cloud-based web portal. It uses state-of-the-art AI algorithms, developed in collaboration with leading retina experts, with a four-step deep convolutional neural network (DCNN). This neural network helps detect the RD stage and annotate lesions based on pixel density in fundus images.